incu6us/goimports-reviser

Right imports sorting & code formatting tool (goimports alternative)

513

Generated Behavioral Tests

99.2%

Best Score

Muse Wonder Full

Results by Model

Hover for details · Click a model to open it · Drag to zoom the x-axis · Shift-drag to pan · The line marks the Pareto frontier (best score per cost)

30 runs

#	Model	Score	Cost	Calls
1	Muse Wonder Full	99.2%	TBA	239	trace →
2	Muse Wonder (xhigh)	97.5%	$25.02	308	trace →
3	Claude Opus 5.5 (xhigh)	96.7%	$26.27	284	trace →
4	GPT 6 Astra (max)	96.3%	$6.56	39	trace →
5	Claude Fable 5.1 (xhigh)	95.7%	$27.29	222	trace →
6	GPT 5.5 (xhigh)	89.7%	$9.03	101	trace →
7	GPT-5.6 Sol (xhigh)	89.5%	$3.31	37	trace →
8	Claude Opus 4.8 (xhigh)	86.6%	$22.84	194	trace →
9	Claude Opus 4.7	86.4%	$2.60	95	trace →
10	Muse Spark 1.3 (max)	76.8%	$4.59	393	trace →
11	Gemini 3.5 Flash	75.4%	$4.75	188	trace →
12	Claude Opus 5 (xhigh)	74.9%	$42.42	324	trace →
13	Muse Spark 1.3 (xhigh)	74.9%	$1.60	259	trace →
14	Gemini 3.7 Flash	74.1%	$1.45	134	trace →
15	Gemini 3 Flash	74.1%	$0.34	121	trace →
16	GPT 5.4	73.3%	$0.60	18	trace →
17	Claude Sonnet 4.6	72.3%	$17.06	441	trace →
18	Claude Opus 4.7 (xhigh)	71.2%	$14.92	266	trace →
19	GLM-5.2	70.9%	$32.72	276	trace →
20	Gemini 3.6 Flash	70.8%	$3.29	152	trace →
21	Muse Spark 1.1 (xhigh)	69.6%	$0.90	120	trace →
22	GPT 5.5 (high)	69.4%	$1.91	21	trace →
23	Claude Opus 4.6	68.6%	$9.52	230	trace →
24	Muse Spark 1.2 (xhigh)	63.2%	$2.17	290	trace →
25	GPT 5.5	59.8%	$1.27	24	trace →
26	GPT-5.6 Sol	59.1%	$1.50	21	trace →
27	Claude Haiku 4.5	46.6%	$1.02	146	trace →
28	GPT 5.4 mini	14.4%	$0.03	11	trace →
29	GPT 5 mini	8.2%	$0.02	12	trace →
30	Gemini 3.1 Pro	0.0%	$1.17	98	trace →

Click a row to replay how that model rebuilt this program, or the model name to open its full run